Skip to main content
BenchLM
Advertise

Benchmark profile

ERQA

A grounded visual reasoning benchmark focused on evidence-based question answering over real images.

Data verified

The public ERQA snapshot ranks Qwen3.7 Plus first at 69.8%, ahead of Gemini 3.1 Pro (69.4%) and GPT-5.4 (65.4%) among 7 tested models. We mirror the table as display-only evidence; it does not affect overall rankings.

Benchmark score on ERQA — July 23, 2026

BenchLM mirrors the published score view for ERQA. Qwen3.7 Plus leads the public snapshot at 69.8% , followed by Gemini 3.1 Pro (69.4%) and GPT-5.4 (65.4%). BenchLM does not use these results to rank models overall.

1Closed

Qwen3.7 Plus

Alibaba

qwen3-7-plus

69.8%
Overall 67.22Context 1M
2Closed

Gemini 3.1 Pro

Google

gemini-3-1-pro

69.4%
Overall 55.3Context 1M
3Closed

GPT-5.4

OpenAI

gpt-5-4

65.4%
Overall 74.24Context 1.05M
7 modelsMultimodal & GroundedCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (7 models)

Score
1
Qwen3.7 PlusAlibaba · Closed
69.8%
2
Gemini 3.1 ProGoogle · Closed
69.4%
3
GPT-5.4OpenAI · Closed
65.4%
4
Muse SparkMeta · Closed
64.7%
5
Qwen3.6-27BAlibaba · Open weight
62.5%
6
Grok 4.20xAI · Closed
54.1%
7
Claude Opus 4.6Anthropic · Closed
51.6%

The published ERQA snapshot places Qwen3.7 Plus first at 69.8%. The third row is 4.4 points behind. The broader top-10 range is 18.2 points, so the table still separates the published systems.

7 models have been evaluated on ERQA. The benchmark falls in the Multimodal & Grounded category. This category carries a 12% weight in BenchLM.ai's overall scoring system. ERQA is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About ERQA

Year

2026

Tasks

Evidence-based visual QA

Format

Grounded image reasoning

Difficulty

Grounded multimodal reasoning

ERQA is useful as a grounded reasoning check because it emphasizes answer correctness tied to visual evidence rather than fluent but ungrounded descriptions.

Qwen3.6 launch benchmarks

BenchLM freshness & provenance

Version

ERQA 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does ERQA measure?

A grounded visual reasoning benchmark focused on evidence-based question answering over real images.

Which model scores highest on ERQA?

Qwen3.7 Plus by Alibaba currently leads with a score of 69.8% on ERQA.

How many models are evaluated on ERQA?

7 AI models have been evaluated on ERQA on BenchLM.

Compare Top Models on ERQA

Qwen3.7 Plus vs Gemini 3.1 ProGemini 3.1 Pro vs GPT-5.4GPT-5.4 vs Muse SparkMuse Spark vs Qwen3.6-27B
Last updated: July 23, 2026 · BenchLM version ERQA 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.